Community

• 

  Helen Osetrova

  • August 31, 2018 11:57

  Hello!

   

  Could you please tell us more about your processing scenario? What kind of signatures do you need to extract: handwritten, digital or something else? It would be great if you attach a sample document to your message.

  No 0 Yes
• 

  Permanently deleted user

  • September 17, 2018 07:28

  Hi Helen,

  I need to extract handwritten signature. Is this possible with abby?

   

  Thanks,

  Vidhya.

  No 0 Yes
• 

  Helen Osetrova

  • September 20, 2018 17:02

  Hi Vidhya,

   

   

  ABBYY OCR technologies allow recognizing a handwritten text only if the characters are separated and written as single characters (so-called "handprinted text"). The letters in signatures are usually distorted and written together, so it is not possible to recognize them and signatures appear in the result file as pictures.

   

  Hope this answers your query.

   

  No 0 Yes
• 

  Permanently deleted user

  • October 15, 2018 10:56

  Hello,

   

  Can I extract image from PDF document by using OCR SDK API?

  No 0 Yes
• 

  Helen Osetrova

  • October 19, 2018 15:58

  Hello Ibrahim, 

   

  In order to extract only images from your document, please follow several steps:

  • perform the document preprocessing and the document analysis;
  • obtain an actual page layout as an ILayout object;
  • check its blocks one by one and remove the ones which type is not BT_RasterPicture. 

   

  Please find below the code snippet that illustrates the suggested approach: 

   

   

  // Java code sample
  // We assume that FREngine is loaded and document analysis is performed
  
  IFRPages frPages = document.getPages();
  int pagesCount = frPages.getCount();
  
  for (int j =0; j < pagesCount; j++) {
  
       IFRPage page = frPages.getElement(j);
       ILayout pageLayout = page.getLayout();
       ILayoutBlocks blocks = pageLayout.getBlocks();
       int blocksCount = blocks.getCount();
       int i =0;
  
        while (i < blocksCount) {
  
            IBlock block = blocks.getElement(i);
            displayMessage( "Checking blocks");
            BlockTypeEnum blockType = block.getType();
  
            if (blockType != BlockTypeEnum.BT_RasterPicture) {
  
               displayMessage( "Delete block");
               blocks.DeleteAt(i);
               blocksCount = blocks.getCount();
               continue;
  
            }
  
        i++;
        } // iterating blocks
  
  displayMessage( "Recognize page...");
  page.Recognize(null, null);
  
  } // iterating pages
  
  ...

   

  Please also review the topic about tables extraction where the same approach is used: https://forum.ocrsdk.com/thread/tables-only-from-pdf/. You can find more details of different stages of document processing in FineReader Engine in the Developer's Help → Guided Tour → Advanced Techniques → Tuning Parameters of Page Preprocessing, Analysis, Recognition, and Synthesis article.

   

  Hope this information will be helpful!

   

  No 0 Yes

Please sign in to leave a comment.